Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets
This paper proposes a novel solution for separating an unknown and time-varying number of moving acoustic sources in a blind setting using multiple microphone arrays. A standard steered-response power phase transform method is applied to extract source position measurements, which inevitably contain...
| Main Authors: | , , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
2021
|
| Subjects: | |
| Online Access: | http://purl.org/au-research/grants/arc/DP170104854 http://hdl.handle.net/20.500.11937/90800 |
| _version_ | 1848765431869865984 |
|---|---|
| author | Ong, Jonah Vo, Ba Tuong Nordholm, Sven |
| author_facet | Ong, Jonah Vo, Ba Tuong Nordholm, Sven |
| author_sort | Ong, Jonah |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper proposes a novel solution for separating an unknown and time-varying number of moving acoustic sources in a blind setting using multiple microphone arrays. A standard steered-response power phase transform method is applied to extract source position measurements, which inevitably contain noise, false detections, missed detections, and are not labeled with the source identities. The imperfect measurements lead to the space-time permutation problem, as there is no information on how the measurements are associated to the sources in space, nor how the measurements are connected across time, if at all. To solve this problem, a labeled random finite set tracking framework is adopted to jointly estimate the source positions and their labels or identities. Based on these trajectory estimates, a corresponding set of time-varying generalized side-lobe cancellers is constructed to perform source separation. The overall algorithm operates in a block-wise or an online fashion and is scalable with the number of microphone arrays. The quality of the measurements, tracking, and separation, are evaluated respectively, with the OSPA metric, OSPA(2) metric, and ITU-T P.835 based listening tests, on both real-world and simulated data. |
| first_indexed | 2025-11-14T11:35:09Z |
| format | Journal Article |
| id | curtin-20.500.11937-90800 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T11:35:09Z |
| publishDate | 2021 |
| publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-908002023-04-24T01:34:32Z Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets Ong, Jonah Vo, Ba Tuong Nordholm, Sven Science & Technology Technology Acoustics Engineering, Electrical & Electronic Engineering Time measurement Position measurement Microphone arrays Noise measurement Acoustic measurements Trajectory Blind source separation multi-object tracking labeled random finite sets acoustic localization spatial filtering TIME-VARYING NUMBER ACOUSTIC SOURCE TRACKING IMPLEMENTATION ALGORITHMS SPEAKERS This paper proposes a novel solution for separating an unknown and time-varying number of moving acoustic sources in a blind setting using multiple microphone arrays. A standard steered-response power phase transform method is applied to extract source position measurements, which inevitably contain noise, false detections, missed detections, and are not labeled with the source identities. The imperfect measurements lead to the space-time permutation problem, as there is no information on how the measurements are associated to the sources in space, nor how the measurements are connected across time, if at all. To solve this problem, a labeled random finite set tracking framework is adopted to jointly estimate the source positions and their labels or identities. Based on these trajectory estimates, a corresponding set of time-varying generalized side-lobe cancellers is constructed to perform source separation. The overall algorithm operates in a block-wise or an online fashion and is scalable with the number of microphone arrays. The quality of the measurements, tracking, and separation, are evaluated respectively, with the OSPA metric, OSPA(2) metric, and ITU-T P.835 based listening tests, on both real-world and simulated data. 2021 Journal Article http://hdl.handle.net/20.500.11937/90800 10.1109/TASLP.2021.3087003 English http://purl.org/au-research/grants/arc/DP170104854 http://creativecommons.org/licenses/by/4.0/ IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC fulltext |
| spellingShingle | Science & Technology Technology Acoustics Engineering, Electrical & Electronic Engineering Time measurement Position measurement Microphone arrays Noise measurement Acoustic measurements Trajectory Blind source separation multi-object tracking labeled random finite sets acoustic localization spatial filtering TIME-VARYING NUMBER ACOUSTIC SOURCE TRACKING IMPLEMENTATION ALGORITHMS SPEAKERS Ong, Jonah Vo, Ba Tuong Nordholm, Sven Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title | Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title_full | Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title_fullStr | Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title_full_unstemmed | Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title_short | Blind Separation for Multiple Moving Sources with Labeled Random Finite Sets |
| title_sort | blind separation for multiple moving sources with labeled random finite sets |
| topic | Science & Technology Technology Acoustics Engineering, Electrical & Electronic Engineering Time measurement Position measurement Microphone arrays Noise measurement Acoustic measurements Trajectory Blind source separation multi-object tracking labeled random finite sets acoustic localization spatial filtering TIME-VARYING NUMBER ACOUSTIC SOURCE TRACKING IMPLEMENTATION ALGORITHMS SPEAKERS |
| url | http://purl.org/au-research/grants/arc/DP170104854 http://hdl.handle.net/20.500.11937/90800 |